Exploring Uncore Frequency Scaling for Heterogeneous Computing
Zhong Zheng, Seyfal Sultanov, Michael E. Papka, Zhiling Lan

TL;DR
This paper introduces MAGUS, a runtime system that dynamically scales uncore frequency in heterogeneous CPU-GPU systems to reduce power consumption and improve energy efficiency without significantly impacting performance.
Contribution
MAGUS is a novel, user-transparent runtime that effectively tunes uncore frequency in heterogeneous systems, addressing the complexity of phase detection and application diversity.
Findings
Achieves up to 27% energy savings.
Reduces energy-delay product by 26%.
Maintains performance loss below 5%.
Abstract
High-performance computing (HPC) systems are essential for scientific discovery and engineering innovation. However, their growing power demands pose significant challenges, particularly as systems scale to the exascale level. Prior uncore frequency tuning studies have primarily focused on conventional HPC workloads running on homogeneous systems. As HPC advances toward heterogeneous computing, integrating diverse GPU workloads on heterogeneous CPU-GPU systems, it is crucial to revisit and enhance uncore scaling. Our investigation reveals that uncore frequency scales down only when CPU power approaches its TDP (Thermal Design Power), an uncommon scenario in GPU-dominant applications, resulting in unnecessary power waste in modern heterogeneous computing systems. To address this, we present MAGUS, a user-transparent uncore frequency scaling runtime for heterogeneous computing. Effective…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsNeural Networks and Applications
